Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Department of Biomedical Engineering, Faculty of Engineering, Shahed University, Tehran, Iran.
Biomed Phys Eng Express. 2021 Jan 29;7(2). doi: 10.1088/2057-1976/abdbbc.
Color Vision Deficiency (CVD) is one of the most common types of vision deficiency. People with CVD have difficulty seeing color spectra depending on what types of retina photoreceptors are impaired. In this paper, the Ishihara test with 38 plates was used to examine the Electroencephalogram (EEG) of ten subjects with CVD plus ten healthy individuals. The recording was performed according to the 10-20 international system. The C-based software was programmed so that subjects could select the number or path in each test plate in the software options while recording EEG. Frequency features in different frequency bands were extracted from the EEG signals of the two groups during the Ishihara test. Statistically significant differences (P < 0.05) between features were assessed by independent samples t-test with False Discovery Rate (FDR) correction. Also, the K-nearest neighbor classifier (KNN) was used to classify the two groups. The results revealed that the most significant difference between the two groups in the Ishihara test images occurred for the electrodes located in the right temporoparietal areas (P4 and T6) of the brain in the Delta, Theta, Beta1, and Beta2 frequency bands. The KNN classifier, using the signals that reported the greatest statistical difference between the two groups, showed that the two groups were distinguishable with 85.2% accuracy. In this way, images from the Ishihara test that would provide the most accurate classification were identified. In conclusion, this research provided new insights into EEG signals of subjects with CVD and healthy subjects based on the Ishihara color vision test.
色觉缺陷（CVD）是最常见的视力缺陷之一。患有 CVD 的人根据受损的视网膜光感受器类型，难以看到色觉光谱。在本文中，使用了 38 个板的石原氏测试来检查 10 名 CVD 患者和 10 名健康个体的脑电图（EEG）。记录是根据 10-20 国际系统进行的。基于 C 的软件进行了编程，以便在记录 EEG 的同时，受试者可以在软件选项中选择每个测试板的数字或路径。从两组在石原氏测试期间的 EEG 信号中提取了不同频带中的频率特征。通过独立样本 t 检验（具有 False Discovery Rate（FDR）校正）评估了两组之间特征的统计学显着差异（P <0.05）。还使用了 K-最近邻分类器（KNN）对两组进行分类。结果表明，在石原氏测试图像中，两组之间最显着的差异发生在大脑右颞顶区域（P4 和 T6）的 Delta、Theta、Beta1 和 Beta2 频带中的电极上。KNN 分类器使用两组之间报告的最大统计差异的信号，显示两组的准确率为 85.2%。通过这种方式，确定了能够提供最准确分类的石原氏测试图像。总之，这项研究基于石原氏色觉测试，为 CVD 患者和健康受试者的 EEG 信号提供了新的见解。
